An Enhanced Medical Diagnosis System for Malaria and Typhoid Fever Using Genetic Neuro-Fuzzy System

Abstract

The major challenge of inadequate healthcare services in developing countries has been linked to the unavailability of qualified medical personnel and inefficient diagnostic techniques adopted. The advent of technology in medicine has aided the improvement of medical processes including diagnosis. Many computerized systems have been implemented over the years for medical diagnosis some of which included machine learning techniques. But the existing methods lack the power of selecting the most relevant signs and symptoms of malaria and typhoid fever. Therefore, this study develops a system capable of Malaria and Typhoid Fever diagnosis using a Genetic Algorithm, a Neuro-Fuzzy Inference System called GENFIS. In order to train the NFIS, the GA module determines the optimal set of network parameters, saves them, and then distributes them to the appropriate hidden layer nodes. The study made use of the MATLAB environment to test and evaluate the system. The accuracy performance of the proposed model revealed an accuracy of 97.2%, thus performing better than some of the existing systems. If completely adopted, the proposed approach has the potential to lessen the major issues with NFIS systems. Furthermore, it might be used to address difficult issues in different fields.